arXiv:2602.11204v1 Announce Type: new Abstract: The widespread use of publicly available pre-trained encoders from self-supervised learning (SSL) has exposed a critical vulnerability: their susceptibility to downstream-agnostic adversarial examples (DAEs), which are crafted without knowledge of the downstream tasks but capable of misleading downstream models. While several defense methods have been explored recently, they rely primarily on task-specific adversarial fine-tuning, which inevitably limits generalizability and causes catastrophic forgetting and deteriorates benign performance. Different with previous works, we propose a […]

Ver mais

Self-supervised learning (SSL) faces a fundamental conflict between semantic understanding and image reconstruction. High-level semantic SSL (e.g., DINO) relies on global tokens that are forced to be location-invariant for augmentation alignment, a process that inherently discards the spatial coordinates required for reconstruction. Conversely, generative SSL (e.g., MAE) preserves dense feature grids for reconstruction but fails to produce high-level abstractions. We introduce STELLAR, a framework that resolves this tension by factorizing visual features into a low-rank product of semantic […]

Ver mais

arXiv:2603.05647v1 Announce Type: new Abstract: People experiencing mental health crises frequently turn to open-ended generative AI (GenAI) chatbots such as ChatGPT for support. However, rather than providing immediate assistance, most GenAI chatbots are designed to respond to crisis situations in ways that minimize their developers’ liability, primarily through avoidance (e.g., refusing to engage beyond templated referrals to crisis hotlines). Withholding crisis support in these cases may harm users who have no viable alternatives and reduce their motivation to […]

Ver mais

Introduction Disclaimer: This article is a cross post from Pytorch Medium Blog Post. One of the most exciting advancements, that has pushed the frontier of the Artificial Intelligence (AI) in recent years, is Deep Reinforcement Learning (DRL). DRL belongs to the family of machine learning algorithms. It assumes that intelligent machines can learn from their actions similar to the way humans learn from experience. Over the recent years we could witness some impressive real-world applications of DRL. The […]

Ver mais

arXiv:2601.05449v1 Announce Type: new Abstract: The increasing deployment of small Uncrewed Aerial Systems (sUAS) in diverse and often safety-critical environments demands rigorous validation of onboard decision logic under various conditions. In this paper, we present SaFUZZ, a state-aware fuzzing pipeline that validates core behavior associated with state transitions, automated failsafes, and human operator interactions in sUAS applications operating under various timing conditions and environmental disturbances. We create fuzzing specifications to detect behavioral deviations, and then dynamically generate associated […]

Ver mais

The Parzen-window method (also known as Parzen-Rosenblatt window method) is a widely used non-parametric approach to estimate a probability density function *p(**x**)* for a specific point *p(**x**)* from a sample *p(**x**n)* that doesn’t require any knowledge or assumption about the underlying distribution.

Ver mais

arXiv:2602.17682v1 Announce Type: new Abstract: Consistency-based generative models like Shortcut and MeanFlow achieve impressive results via a target-aware design for solving the Probability Flow ODE (PF-ODE). Typically, such methods introduce a target time $r$ alongside the current time $t$ to modulate outputs between a local multi-step derivative ($r = t$) and a global few-step integral ($r = 0$). However, the conventional “one input, one output” paradigm enforces a partition of the training budget, often allocating a significant portion […]

Ver mais

I received a lot of positive feedback about the step-wise Principal Component Analysis (PCA) implementation. Thus, I decided to write a little follow-up about Linear Discriminant Analysis (LDA) — another useful linear transformation technique. Both LDA and PCA are commonly used dimensionality reduction techniques in statistics, pattern classification, and machine learning applications. By implementing the LDA step-by-step in Python, we will see and understand how it works, and we will compare it to a PCA to see how […]

Ver mais

arXiv:2601.15423v1 Announce Type: new Abstract: We introduce Lattice, a hybrid sequential prediction system that conditionally activates learned behavioral structure using binary confidence gating. The system clusters behavior windows into behavioral archetypes and uses binary confidence gating to activate archetype-based scoring only when confidence exceeds a threshold, falling back to baseline predictions when uncertain. We validate Lattice on recommendation systems (MovieLens), scientific time-series (LIGO), and financial markets, using LSTM and transformer backbones. On MovieLens with LSTM, Lattice achieves +31.9% […]

Ver mais

Fraudulent activities on digital banking services are becoming more intricate by the day, challenging existing defenses. While older rule driven methods struggle to keep pace, even precision focused algorithms fall short when new scams are introduced. These tools typically overlook subtle shifts in criminal behavior, missing crucial signals. Because silent breaches cost institutions far more than flagged but legitimate actions, catching every possible case is crucial. High sensitivity to actual threats becomes essential when oversight leads to heavy […]

Ver mais